NAME: The ICU Data
KEYWORDS: Logistic Regression
SIZE: 200 observations, 21 variables
NOTE:
These data come from Hosmer and Lemeshow (2000) Applied Logistic
Regression: Second Edition. These data are copyrighted by John Wiley &
Sons Inc. and must be acknowledged and used accordingly.
DESCRIPTIVE ABSTRACT:
The ICU data set consists of a sample of 200 subjects who were part of
a much larger study on survival of patients following admission to an adult
intensive care unit (ICU). The major goal of this study was to develop a
logistic regression model to predict the probability of survival to hospital
discharge of these patients and to study the risk factors associated with
ICU mortality. A number of publications have appeared which have focused on
various facets of the problem. The reader wishing to learn more about the
clinical aspects of this study should start with Lemeshow, Teres, Avrunin,
and Pastides (1988).
SOURCE: Data were collected at BaystateMedicalCenter in Springfield,
Massachusetts.
Table: Code Sheet for the ICU Data.
Column
Position NameCodes/ValuesAbbreviations
------
6-8Identification CodeID NumberID
11Vital Status0 = LivedSTA
1 = Died
14-15AgeYearsAGE
18Sex0 = MaleSEX
1 = Female
21Race1 = WhiteRACE
2=Black
3 = Other
24Service at ICU Admission0 = MedicalSER
1 = Surgical
27Cancer Part of Present0 = NoCAN
Problem1 = Yes
30History of Chronic RenalO = NoCRN
Failure1 = Yes
33Infection Probable at ICU0 = NoINF
Admission1 = Yes
36CPR Prior to ICU Admission0 = NoCPR
1 = Yes
39-41Systolic Blood Pressure atmm HgSYS
ICU Admission
44-46Heart Rate at ICU AdmissionBeats/minHRA
49Previous Admission to an ICU0 = NoPRE
within 6 Months1 = Yes
52Type of Admission0 = ElectiveTYP
1 = Emergency
55Long Bone, Multiple, Neck,0 = NoFRA
Single Area, or Hip Fracture1 = Yes
58PO2 from Initial Blood Gases0 = > 60PO2
1 = < 60
61PH from Initial Blood Gases0 => 7.25PH
1 =< 7.25
64PCO2 from initial Blood0 = < 45PCO
Gases1 = > 45
67Bicarbonate from Initial0 = > 18BIC
Blood Gases1 = < 18
70Creatinine from Initial Blood0 = < 2.0CRE
Gases1 = > 2.0
73Level of Consciousness at ICUO = No ComaLOC
Admissionor Stupor
1 = Deep
stupor
2 = Coma
------
PEDAGOGICAL NOTES:
These data have been used to fit an ordinary logistic regression
model and for various exercises involving logistic regression.
REFERENCES:
1. Hosmer and Lemeshow, Applied Logistic Regression, Wiley, (1989).
2. Lemeshow, S., Teres, D., Avrunin, J. S., Pastides, H. (1988). Predicting
the Outcome of Intensive Care Unit Patients. Journal of the American
Statistical Association, 83, 348-356.